© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 3522
    Prev
    Next
    INDEX
    Explanations

    references to humanoid creatures or characters

    oai_token-act-pair · gpt-3.5-turbo

    references to humanoid creatures and their classifications in fantasy or role-playing contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pins
    -0.87
    apeake
    -0.85
    orship
    -0.84
    agall
    -0.82
    obyl
    -0.76
    clip
    -0.76
    jamin
    -0.75
    obos
    -0.75
    pin
    -0.74
    quote
    -0.73
    POSITIVE LOGITS
     denomin
    0.67
     Revival
    0.66
    Reloaded
    0.65
     intermediate
    0.60
    bane
    0.59
    llan
    0.57
    ORPG
    0.57
     ILCS
    0.57
     encount
    0.56
     corrections
    0.55
    Activations Density 0.079%

    No Known Activations